agentmods.dev

biomcp AGENTS.md

Repository instructions for BioMCP, a Rust command-line tool and MCP server for accessing biological data, with Python checks and documentation contracts.

In plain words
What is it for?
Running lint, tests, and specification checks, and changing the Rust, Python, command-line, MCP, or documentation contract safely.
Why use it?
They define the required quality gates and executable specifications so code, documentation, and the shipped interface stay consistent.

Instructions file for CodexOpenCode

615 yesterday A scan 462 tokens original MIT
View the source file genomoncology/biomcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/genomoncology/biomcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/genomoncology/biomcp

Made for: Codex, OpenCode.

Per session 462 This file is loaded in full into every session.
When invoked 462 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00462 $0.00462
Opus 5 $0.00231 $0.00231
Sonnet 5 $0.00092 $0.00092
Haiku 4.5 $0.00046 $0.00046

Measured yesterday against content hash 9c7054c78653, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

biomcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 70 lines

What it actually says

AGENTS.md — BioMCP

BioMCP is a Rust CLI and MCP server with a Python docs/contract harness. The Rust runtime lives under src/; Python tests, docs checks, and executable contracts exercise the shipped CLI/MCP surface.

Repository contract shape

  • Behavioral contracts are mustmatch executable docs at:

    spec/*.md

    Run them with make spec. The spec gates use the standalone mustmatch test binary through scripts/run-specs.sh. Cargo artifact preparation and fixture standup belong in the runner and scripts/prepare-spec-artifacts.py, not in ad hoc docs. Specification pages execute prepared paths and must not invoke cargo run, cargo build, cargo rustc, cargo test, cargo tree, or cargo metadata.

  • Unit/static layers run with make test: Rust nextest first, then the Python CLI/MCP/docs contract lane.

Contract quick reference

spec/*.md make lint make test make spec rust-standards python-standards cli-design mustmatch testing-mindset

Gates

Run the standard gates directly:

make lint
make test
make spec

There is intentionally no make check convention. make lint includes the quality ratchet, make test includes both Rust and Python contract tests, and make spec is the routine mustmatch contract gate.

Routine gates use --no-default-features so lint, test, and spec share one small Cargo graph; that graph does not exercise AlphaGenome. Run make full-feature-check for all shipped features and the AlphaGenome behavior tests. make release-gate includes both lanes.

Skill rail

Use this hybrid repo rail for dispatched work:

  • rust-standards
  • python-standards
  • cli-design
  • mustmatch
  • testing-mindset

Hygiene

Do not commit secrets, PHI, absolute local paths, planning notes, or March runtime artifacts. Keep .march/ runtime state, .march-runtime/, local caches, and generated build outputs out of git.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 70 lines · 462 tokens per session scan A 9c7054c78653

Subscribe to this mod's changes

biomcp AGENTS.md is an instructions file published in the GitHub repository genomoncology/biomcp (615 stars, last pushed yesterday), licensed MIT. It adds 462 tokens to every session, about $0.0023 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code reviewData and AILLMTestingaibioinformaticsclinical-trialsgenomicsmcp
Related

Other instructions, from other repositories

DNAnalyzer AGENTS.md

Instructions for VerisimilitudeX/DNAnalyzer, covering agent guide, what this repository is, canonical references for agents, build and verify and conventions that agents frequently get wrong.

VerisimilitudeX/DNAnalyzer · 1,306 tokens

autozyme CLAUDE.md

Instructions for ElliotXie/autozyme, covering autozyme, layout, how to use, environment and cli quick reference.

ElliotXie/autozyme · 289 tokens

ClawBio AGENTS.md

AGENTS.md instructions for ClawBio/ClawBio, covering agents.md — clawbio guide for ai coding agents, project overview, setup, clone and install dependencies.

ClawBio/ClawBio · 2,854 tokens

SciAgent-Skills AGENTS.md

AGENTS.md instructions for jaechang-hits/SciAgent-Skills, covering skills — workflow guide, directory layout, workflow: topic → entry (5 steps), step 2. choose category and step 3. gather reference material.

jaechang-hits/SciAgent-Skills · 6,399 tokens

mosaicatcher-pipeline CLAUDE.md

Claude Code instructions for friendsofstrandseq/mosaicatcher-pipeline, covering claude.md, project overview, version management, common commands and using pixi (recommended for snakemake v9+).

friendsofstrandseq/mosaicatcher-pipeline · 2,458 tokens

mosaicatcher-pipeline GEMINI.md

Gemini CLI instructions for friendsofstrandseq/mosaicatcher-pipeline, covering claude.md, project overview, version management, common commands and using pixi (recommended for snakemake v9+).

friendsofstrandseq/mosaicatcher-pipeline · 2,434 tokens